© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11836
    Prev
    Next
    INDEX
    Explanations

    words or phrases that mean something is wrong

    oai_token-act-pair · gemini-2.0-flash

    problem or question

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -1.98
    '
    -0.74
    ↵↵
    -0.72
     
    -0.68
    ↵
    -0.66
     and
    -0.60
    ’
    -0.60
    s
    -0.60
    1
    -0.59
    "
    -0.56
    POSITIVE LOGITS
    +#+#
    1.23
     snippetHide
    1.10
    tvguidetime
    1.04
    UserScript
    1.02
    WebElementEntity
    0.98
    -------------</
    0.96
     protoimpl
    0.92
     HasFactory
    0.92
     referrerpolicy
    0.91
    AnchorStyles
    0.91
    Activations Density 0.508%

    No Known Activations