© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14031
    Prev
    Next
    INDEX
    Explanations

    the word "safety"

    oai_token-act-pair · gemini-2.0-flash

    safety

    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
    Negative Logits
    er
    -0.75
    en
    -0.70
    un
    -0.65
    (
    -0.65
    em
    -0.65
    in
    -0.64
    on
    -0.63
    I
    -0.63
     unſ
    -0.60
    <b>
    -0.59
    POSITIVE LOGITS
    ########.
    1.13
    uxxxx
    1.02
     CreateTagHelper
    1.02
    SPATH
    1.00
     Roskov
    0.99
    WebControls
    0.97
     nakalista
    0.94
    //
    0.93
     ControllerBase
    0.92
    ---*/
    0.90
    Activations Density 1.857%

    No Known Activations