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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 3182
    Prev
    Next
    INDEX
    Explanations

    best fits your

    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
    ب
    1.14
     descre
    1.07
     relativi
    0.97
    BtnFill
    0.95
     Leveraging
    0.95
    ৌম
    0.94
    තුරු
    0.94
    ributed
    0.94
    였
    0.94
     Headlines
    0.93
    POSITIVE LOGITS
    er
    1.10
     справи
    0.95
    ென
    0.94
    ル
    0.90
     scientifiques
    0.88
    ος
    0.88
    ام
    0.87
    alat
    0.87
    па
    0.85
    ILL
    0.85
    Activations Density 0.214%

    No Known Activations