© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 175470
    Prev
    Next
    INDEX
    Explanations

    replacement or modification

    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_24_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
     yapmak
    0.45
     katth
    0.45
    🗯
    0.45
     satisfacer
    0.43
    GetData
    0.43
     bestimmen
    0.43
     уйнарга
    0.42
     coasters
    0.42
    गुन
    0.42
    выя
    0.42
    POSITIVE LOGITS
     Labs
    0.46
    ítě
    0.45
    0.44
     (
    0.42
     Ab
    0.42
     Lessons
    0.42
    ang
    0.41
     Lancet
    0.41
    笃
    0.41
     Example
    0.40
    Activations Density 0.000%

    No Known Activations