© 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
    2. Gemma-3-4B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 3509
    Prev
    Next
    INDEX
    Explanations

    California

    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
    ɓ
    1.26
     arme
    1.10
     secondly
    1.07
    ᴀ
    1.05
    🅽
    1.04
     delante
    1.04
    િયા
    1.04
     retour
    1.04
    
    1.03
    ᴏ
    1.03
    POSITIVE LOGITS
     Unified
    1.18
     California
    1.15
    stituting
    1.11
     Californie
    1.08
    യി
    1.07
    ้
    1.06
    classed
    1.06
    //////////////
    1.05
    ating
    1.04
     Calif
    1.03
    Activations Density 0.137%

    No Known Activations