© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23312
    Prev
    Next
    INDEX
    Explanations

    map or answer marker

    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
     तुमसे
    0.42
     तुम्ही
    0.41
     तुम्हाला
    0.41
     يمكنك
    0.37
     তুমি
    0.36
    <unused985>
    0.36
     तुम्हारी
    0.36
     тобой
    0.36
    想不到
    0.35
     Prefer
    0.35
    POSITIVE LOGITS
     Map
    1.02
    Map
    1.01
     map
    0.98
     mapping
    0.95
    map
    0.93
     MAP
    0.89
     Mapping
    0.88
    맵
    0.87
    MAP
    0.86
     maps
    0.85
    Activations Density 0.004%

    No Known Activations