© 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. 10473
    Prev
    Next
    INDEX
    Explanations

    the word "directly" and sometimes "indirectly".

    oai_token-act-pair · gemini-2.0-flash

    directly

    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
    INGEN
    -0.69
    ]--;
    -0.67
     مشين
    -0.63
    IFICATE
    -0.61
    alisation
    -0.60
    ophone
    -0.58
     Sie
    -0.58
    WithMany
    -0.58
     sie
    -0.57
    AGUE
    -0.57
    POSITIVE LOGITS
    <bos>
    2.03
    '
    0.60
    ’
    0.56
    ValueStyle
    0.55
     contributions
    0.52
     quæ
    0.51
    “
    0.50
     whither
    0.48
     للمعارف
    0.48
     snabbt
    0.47
    Activations Density 0.526%

    No Known Activations