Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 4335
    Prev
    Next
    INDEX
    Explanations

    South Africa

    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_5_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
     Bxa
    1.21
    ช
    1.17
    нансо
    1.16
    ш
    1.11
    ვნ
    1.09
    ্ব
    1.07
    დომ
    1.06
     mitologia
    1.06
     whack
    1.06
     darn
    1.06
    POSITIVE LOGITS
     RCW
    1.09
     utterances
    1.08
    ą
    1.03
    {},
    1.01
     Sono
    0.94
     <%=
    0.93
    каў
    0.92
    "%
    0.92
     AUC
    0.91
    }/>
    0.91
    Activations Density 0.024%

    No Known Activations