© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 143311
    Prev
    Next
    INDEX
    Explanations

    starting or beginning

    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_46_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
    今後
    0.38
    යි
    0.37
    =$_
    0.37
     FAX
    0.37
    бут
    0.37
     Buff
    0.37
    deme
    0.37
    在全球
    0.37
    大使
    0.36
    uther
    0.36
    POSITIVE LOGITS
    蛞
    0.40
     adversity
    0.39
    στ
    0.38
     driftwood
    0.37
    বিক
    0.36
     નિય
    0.36
     recurso
    0.36
    StructOf
    0.36
    স্টি
    0.36
     Webseite
    0.35
    Activations Density 0.007%

    No Known Activations