© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 60073
    Prev
    Next
    INDEX
    Explanations

    how many or much or to or long

    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_2_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
    л
    1.21
     (
    1.16
    ल
    0.95
    나
    0.95
     $
    0.92
     a
    0.91
     Cous
    0.80
    ين
    0.80
    된
    0.80
     Service
    0.79
    POSITIVE LOGITS
    0
    1.36
    <0x80>
    1.35
    ка
    1.34
    ０
    1.30
    er
    1.16
    𝟬
    1.12
    
    1.10
    )”.
    1.03
     mắt
    1.02
    ;
    1.02
    Activations Density 0.000%

    No Known Activations