© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 252590
    Prev
    Next
    INDEX
    Explanations

    locations and districts

    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_56_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
    abilă
    0.40
    Aby
    0.38
    Xml
    0.37
    rég
    0.37
    𝘢
    0.37
    utcnow
    0.37
     trump
    0.37
    álne
    0.37
    opath
    0.37
     úd
    0.37
    POSITIVE LOGITS
    wai
    0.41
    ＃
    0.35
    Ⅲ
    0.34
     FO
    0.34
     Hot
    0.33
     Next
    0.33
    ኪ
    0.33
     CG
    0.32
     Hub
    0.32
     =======
    0.32
    Activations Density 0.000%

    No Known Activations