© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 88275
    Prev
    Next
    INDEX
    Explanations

    squad depth

    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_23_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
     zvý
    0.38
     zwięks
    0.37
    დომ
    0.37
     vru
    0.37
     wygląd
    0.37
     sophistic
    0.36
     ٹیکسٹ
    0.35
    ༸
    0.35
    品番
    0.35
    ffine
    0.35
    POSITIVE LOGITS
     उदा
    0.37
    itano
    0.36
    \_
    0.35
     Alternative
    0.35
     '
    0.34
     Packed
    0.34
     quando
    0.34
     когато
    0.33
     asking
    0.33
     USO
    0.33
    Activations Density 0.000%

    No Known Activations