© 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. 5204
    Prev
    Next
    INDEX
    Explanations

    card, Pay, add, Pen, Health

    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
    ю
    2.90
    textbf
    2.65
    ς
    2.61
    TERS
    2.52
    গণ
    2.51
     eisen
    2.50
    -\
    2.49
    朋友
    2.47
    Instruments
    2.45
     progett
    2.44
    POSITIVE LOGITS
     profinite
    2.68
    nect
    2.48
    wedge
    2.44
    w
    2.37
     NSUTF
    2.37
     arrayOf
    2.36
     listOf
    2.34
     poaching
    2.28
     Noether
    2.27
    }";
    2.25
    Activations Density 0.036%

    No Known Activations