© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 22106
    Prev
    Next
    INDEX
    Explanations

    ;

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    )**
    0.37
    )</
    0.33
    둴
    0.32
    )+"
    0.30
     liten
    0.30
    )}"
    0.30
    )}+\
    0.30
    };\
    0.30
    )");
    0.29
    )}')
    0.29
    POSITIVE LOGITS
    Nú
    0.32
    Tabla
    0.31
    team
    0.30
    BIB
    0.30
    criteria
    0.29
    Enc
    0.29
    getting
    0.29
    worldly
    0.29
    邱
    0.29
    ført
    0.28
    Activations Density 0.001%

    No Known Activations