© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 156707
    Prev
    Next
    INDEX
    Explanations

    pulver

    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
    ,
    1.02
    ’
    0.99
     boxe
    0.98
    ți
    0.92
     recherche
    0.92
    ৯
    0.91
    0.88
    0.88
     schrij
    0.86
     fiets
    0.85
    POSITIVE LOGITS
    m
    2.09
    at
    2.02
    y
    1.70
    l
    1.64
    b
    1.59
    like
    1.55
    3
    1.55
    n
    1.52
    d
    1.52
    r
    1.48
    Activations Density 0.000%

    No Known Activations