© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 236401
    Prev
    Next
    INDEX
    Explanations

    input element attributes

    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_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
    efic
    0.41
    )>=
    0.40
    Brooks
    0.39
    Op
    0.39
     опа
    0.38
    -'+
    0.38
    ૮
    0.38
    )+
    0.37
    beb
    0.37
    য়াম
    0.36
    POSITIVE LOGITS
    ړ
    0.42
     tidak
    0.42
    ที่ไม่
    0.40
    沒有
    0.40
    ヰ
    0.39
     không
    0.38
     não
    0.38
     announcements
    0.38
     Zero
    0.38
     Colin
    0.37
    Activations Density 0.000%

    No Known Activations