© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 213417
    Prev
    Next
    INDEX
    Explanations

    birds

    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_50_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
    brom
    0.44
     lagoons
    0.44
    Mountains
    0.41
     لام
    0.41
    ModelGrid
    0.41
     brom
    0.39
     rent
    0.39
     d
    0.39
     डोंगर
    0.39
     Triangular
    0.39
    POSITIVE LOGITS
    अर्
    0.40
     Compensation
    0.37
     CPM
    0.36
    ucks
    0.36
    ępow
    0.36
     కమి
    0.36
    밴
    0.36
    Ứ
    0.35
    CPR
    0.35
    τυ
    0.34
    Activations Density 0.000%

    No Known Activations