© 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. 5469
    Prev
    Next
    INDEX
    Explanations

    on top of

    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
     rzecz
    1.69
    en
    1.69
    >
    1.68
    ০
    1.65
    к
    1.60
    ؘ
    1.60
     clairement
    1.57
     Antigen
    1.54
     pese
    1.54
    те
    1.48
    POSITIVE LOGITS
     경우
    1.78
    橥
    1.77
     weten
    1.62
     standout
    1.60
    ম
    1.58
    ьте
    1.58
    Strafpunkte
    1.55
    Toe
    1.55
     screws
    1.53
    Personensuche
    1.49
    Activations Density 0.071%

    No Known Activations