© 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. 208156
    Prev
    Next
    INDEX
    Explanations

    place names

    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
     比
    0.46
     glad
    0.38
    仲間
    0.38
     Perm
    0.38
    比
    0.37
    泊
    0.37
    仲
    0.36
    usis
    0.36
    饒
    0.36
    的比
    0.36
    POSITIVE LOGITS
     sch
    0.38
     Gottes
    0.37
    trashButton
    0.35
     Directed
    0.35
     von
    0.35
     schwar
    0.35
     гаранти
    0.35
     Hul
    0.35
     Panzer
    0.35
    𝘵
    0.34
    Activations Density 0.002%

    No Known Activations