© 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. 20907
    Prev
    Next
    INDEX
    Explanations

    organized groups

    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
    ۖ
    0.39
     yer
    0.37
    '`--'`--
    0.36
    stava
    0.35
     troops
    0.34
     يخ
    0.33
    ⿺
    0.33
    };//
    0.33
     আউট
    0.33
     komunitas
    0.33
    POSITIVE LOGITS
     cab
    2.41
     Cab
    1.87
    Cab
    1.82
    cab
    1.70
     cabs
    1.59
     cot
    1.34
     CAB
    1.31
    CAB
    1.20
     clique
    1.02
     cabe
    0.97
    Activations Density 0.062%

    No Known Activations