© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5302
    Prev
    Next
    INDEX
    Explanations

    suffix of Spanish/Portuguese words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vested
    1.49
     числе
    1.47
     dob
    1.46
     fathom
    1.39
    direccion
    1.38
    <bos>
    1.33
    ⎛
    1.31
    SEPARATOR
    1.30
     doom
    1.30
    без
    1.30
    POSITIVE LOGITS
    zame
    1.49
     sparingly
    1.47
     hyvä
    1.42
     precaution
    1.33
    fully
    1.30
    aliases
    1.23
    ून
    1.20
    य
    1.19
    rtype
    1.19
    िता
    1.18
    Activations Density 0.443%

    No Known Activations