© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 7049
    Prev
    Next
    INDEX
    Explanations

    PLZHQOb

    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
     pousse
    0.83
     zwe
    0.73
    𝚅
    0.72
    𝗦
    0.71
    Ϲ
    0.70
    ciamo
    0.69
    री
    0.68
    $;
    0.68
    agoza
    0.68
     kaum
    0.68
    POSITIVE LOGITS
     haunts
    0.90
    Რ
    0.87
     godziny
    0.87
    wreck
    0.86
    said
    0.86
    atherine
    0.83
    resulting
    0.82
    persistent
    0.81
    㞰
    0.81
    jud
    0.80
    Activations Density 0.001%

    No Known Activations