© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40664
    Prev
    Next
    INDEX
    Explanations

    bank, bank nifty, bank robberies, Bank Recovery

    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_11_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
    者は
    0.42
    inį
    0.41
    Ꮻ
    0.38
    者
    0.38
    ⵣ
    0.37
    き
    0.36
    inę
    0.35
     হারে
    0.35
     ड्यू
    0.35
    டர்
    0.34
    POSITIVE LOGITS
    }
    0.41
     गुणा
    0.40
    }>
    0.38
    ByteArray
    0.37
    Rat
    0.37
     označ
    0.37
     Sanskrit
    0.37
    (
    0.36
    Veg
    0.35
    Gum
    0.35
    Activations Density 0.016%

    No Known Activations