© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7646
    Prev
    Next
    INDEX
    Explanations

    the context of pancreatic and abdominal medical issues

    oai_token-act-pair · gemini-2.0-flash

    technical terminology or coding terms

    np_token-act-pair-logits · gpt-4o-mini

    travel/locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Malte
    -0.57
     OSP
    -0.53
     ASR
    -0.52
    marshaller
    -0.52
     Infórmanos
    -0.51
    zeczytaj
    -0.49
     SEDS
    -0.48
     Girona
    -0.47
     Chaldean
    -0.46
     marshmallows
    -0.44
    POSITIVE LOGITS
    ########.
    0.59
    EnumMember
    0.58
    SerializedName
    0.57
    brainly
    0.55
     ivelany
    0.54
    ResumeLayout
    0.53
    httphttps
    0.53
    Bakgrunnsstoff
    0.53
     ujednoznacz
    0.52
    contentValues
    0.52
    Activations Density 1.662%

    No Known Activations