© 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. 208275
    Prev
    Next
    INDEX
    Explanations

    file paths or code

    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
     लाखों
    0.42
     худ
    0.37
     दाम
    0.37
     Quy
    0.37
     پیسہ
    0.36
     Kelsey
    0.36
     disgruntled
    0.35
    怸
    0.35
     loạt
    0.34
    LuaPush
    0.34
    POSITIVE LOGITS
    this
    0.41
    /
    0.38
    ur
    0.36
    .*/
    0.35
     detach
    0.35
     receive
    0.35
    ¹.
    0.35
    `}
    0.34
     (@
    0.33
    状
    0.33
    Activations Density 0.000%

    No Known Activations