© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3736
    Prev
    Next
    INDEX
    Explanations

    personal information and opinions

    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
    ن
    1.28
     FIXME
    1.19
    el
    1.14
    ال
    1.14
     estés
    1.12
    lı
    1.09
    linhas
    1.09
     pronta
    1.07
    се
    1.07
    न
    1.04
    POSITIVE LOGITS
    istic
    1.34
     volition
    1.12
     curiosity
    1.10
     HomePage
    1.09
     pribadi
    1.08
     trzec
    1.08
     metamorphic
    1.07
    bestand
    1.07
     vend
    1.06
     acquainted
    1.05
    Activations Density 0.031%

    No Known Activations