© 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. 5515
    Prev
    Next
    INDEX
    Explanations

    i'm / i'd

    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
    х
    0.77
    𝑐
    0.73
     consummate
    0.59
    מיד
    0.56
     onerous
    0.56
    ल्तान
    0.55
     basing
    0.54
    후
    0.54
     anteriormente
    0.53
    SAG
    0.53
    POSITIVE LOGITS
    いない
    0.72
    daki
    0.71
     mute
    0.65
     tempi
    0.64
     llegar
    0.64
     factura
    0.64
    aaaa
    0.62
    ija
    0.62
    HER
    0.61
     largos
    0.61
    Activations Density 0.007%

    No Known Activations