© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9174
    Prev
    Next
    INDEX
    Explanations

    house, tree

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
     Labs
    0.72
     conscious
    0.71
     labs
    0.71
     Consc
    0.66
    නු
    0.65
     Faw
    0.64
    conscious
    0.63
    흉
    0.63
    arie
    0.63
    ltimes
    0.63
    POSITIVE LOGITS
    house
    1.04
    House
    0.93
    dressing
    0.92
    HOUSE
    0.92
     dressing
    0.83
     house
    0.82
    dress
    0.79
     एले
    0.77
     dresses
    0.75
     HOUSE
    0.74
    Activations Density 0.078%

    No Known Activations