© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12180
    Prev
    Next
    INDEX
    Explanations

    two or three letter sequences

    oai_token-act-pair · gemini-2.0-flash

    medical procedures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    }\]
    -0.76
    UnsafeEnabled
    -0.70
    enterOuterAlt
    -0.68
     NSCoder
    -0.67
     tartalomajánló
    -0.66
    protoimpl
    -0.66
    SharedCtor
    -0.66
    PYX
    -0.65
     Normdatei
    -0.63
    ftagPool
    -0.63
    POSITIVE LOGITS
    AM
    0.68
     AM
    0.62
    am
    0.58
    ams
    0.56
    AMO
    0.55
    AMB
    0.54
    Amo
    0.52
    AMY
    0.52
    ambu
    0.51
     Amic
    0.50
    Activations Density 0.182%

    No Known Activations