© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4971
    Prev
    Next
    INDEX
    Explanations

    sections of documents typically found at the beginning of newspapers or academic papers

    oai_token-act-pair · gemini-2.0-flash

    E

    np_max-act · gemini-2.0-flash

    capital letters

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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>
    -0.87
     mergeFrom
    -0.82
     tartalomajánló
    -0.69
    DIPSETTING
    -0.65
     referenties
    -0.64
     ModelExpression
    -0.62
     Chwiliwch
    -0.59
    homonymie
    -0.58
     SIMBAD
    -0.57
    __':
    -0.57
    POSITIVE LOGITS
     greateſt
    0.56
     tauto
    0.56
     Houſe
    0.53
    CIS
    0.53
    UIL
    0.52
     Theſe
    0.52
     poetical
    0.51
     abstinence
    0.50
    UnusedPrivate
    0.50
     clearness
    0.50
    Activations Density 1.566%

    No Known Activations