© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 82164
    Prev
    Next
    INDEX
    Explanations

    street urchin, Acala

    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_0_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
    ла
    1.75
    า
    1.66
    ,
    1.55
    ა
    1.55
    ू
    1.53
    as
    1.50
    त
    1.50
    are
    1.48
    ll
    1.45
    т
    1.41
    POSITIVE LOGITS
    1.39
     was
    1.32
     Güzel
    1.17
    تق
    1.12
    غة
    1.11
     الرئيس
    1.09
    
    1.08
    ätzen
    1.07
    افة
    1.06
    část
    1.06
    Activations Density 0.000%

    No Known Activations