© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 195504
    Prev
    Next
    INDEX
    Explanations

    deal reached

    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_27_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
     وحدة
    0.36
    Grilled
    0.35
    ಡು
    0.35
    緊
    0.35
     Goff
    0.34
     tightened
    0.33
    pyplot
    0.32
     pública
    0.32
     inescapable
    0.32
     grills
    0.32
    POSITIVE LOGITS
    ဿ
    0.43
    cellcolor
    0.40
    менова
    0.40
     megold
    0.39
    ुरा
    0.38
     harmonique
    0.38
     pasien
    0.36
     bijzonder
    0.36
     एलर्जी
    0.36
     malaysia
    0.36
    Activations Density 0.004%

    No Known Activations