© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10856
    Prev
    Next
    INDEX
    Explanations

    first person language

    oai_token-act-pair · gemini-2.0-flash

    can

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     cannot
    -0.66
     Cannot
    -0.54
     doInBackground
    -0.52
    cannot
    -0.48
     couldn
    -0.48
    BeforeClass
    -0.48
     دى
    -0.46
     unable
    -0.46
    ResumeLayout
    -0.46
    nologue
    -0.44
    POSITIVE LOGITS
     can
    2.33
    can
    1.98
    Can
    1.86
     Can
    1.78
     CAN
    1.34
    CAN
    1.19
    可以
    1.10
     kann
    1.08
     können
    1.07
    可
    1.03
    Activations Density 4.151%

    No Known Activations