© 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-3-27B-IT
    5. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 196651
    Prev
    Next
    INDEX
    Explanations

    Khaled, Khalid, al-Khaldun, Mahmoud, ilea

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_4_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
    u
    1.19
    <0x80>
    1.16
    ן
    0.94
    க்கும்
    0.94
    то
    0.87
     влияния
    0.86
    িম
    0.84
    인이
    0.84
    ד
    0.84
    푞
    0.84
    POSITIVE LOGITS
    S
    1.08
    un
    1.04
    न्
    1.02
    ens
    0.96
    。
    0.95
    ar
    0.94
    SC
    0.94
    SN
    0.92
    ela
    0.92
    )
    0.92
    Activations Density 0.001%

    No Known Activations