© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 130689
    Prev
    Next
    INDEX
    Explanations

    camaraderie

    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_1_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
    c
    1.44
    r
    1.42
    k
    1.41
    durch
    1.35
    ic
    1.27
    d
    1.23
    al
    1.14
    czas
    1.06
    il
    1.05
    ting
    1.05
    POSITIVE LOGITS
     que
    1.30
    ;
    1.29
    A
    1.28
     is
    1.14
    > </
    1.14
    ۰
    1.14
    ר
    1.10
    I
    1.09
    ۸
    1.06
    
    1.06
    Activations Density 0.000%

    No Known Activations