© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 237676
    Prev
    Next
    INDEX
    Explanations

    examples of capabilities

    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_32_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
     개선
    0.39
     escenarios
    0.37
     invester
    0.37
     novelists
    0.36
    Ꮞ
    0.36
     میکر
    0.36
     созна
    0.35
    梢
    0.35
     microorgan
    0.35
     жела
    0.35
    POSITIVE LOGITS
     Invite
    0.39
     invite
    0.39
     Repeat
    0.38
    ily
    0.37
    encing
    0.37
    isini
    0.37
     brag
    0.37
    ênt
    0.37
     यहाँ
    0.36
     expuls
    0.36
    Activations Density 0.011%

    No Known Activations