© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15158
    Prev
    Next
    INDEX
    Explanations

    the word "site" or words related to web content

    oai_token-act-pair · gemini-2.0-flash

    mentions of "site"

    np_token-act-pair-logits · gpt-4o-mini

    site

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    mbh
    -0.57
    abetta
    -0.56
     createState
    -0.56
    ]^{-
    -0.56
    upol
    -0.56
    ogno
    -0.53
    nitzel
    -0.53
    abestanden
    -0.53
    verifyException
    -0.53
    scribe
    -0.52
    POSITIVE LOGITS
    rungsseite
    0.60
     Aérea
    0.56
    FormTagHelper
    0.53
     pagină
    0.52
    rawDesc
    0.49
    rrggbb
    0.49
    DebuggerNonUser
    0.48
    __*/
    0.48
    Personendaten
    0.46
     impegn
    0.46
    Activations Density 6.661%

    No Known Activations