© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214796
    Prev
    Next
    INDEX
    Explanations

    iconic

    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_5_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
    0
    1.88
    <0x80>
    1.60
    ０
    1.36
     बारे
    1.02
     ivvu
    1.01
    nae
    1.00
    yatiti
    0.98
     bhave
    0.98
     nisid
    0.98
    caya
    0.97
    POSITIVE LOGITS
    ä
    1.87
    é
    1.53
    ü
    1.45
    л
    1.30
    ?
    1.27
     at
    1.25
    ə
    1.20
    č
    1.15
    ens
    1.12
    ES
    1.12
    Activations Density 0.001%

    No Known Activations