© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34090
    Prev
    Next
    INDEX
    Explanations

    only X

    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_3_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
    ER
    0.67
    HE
    0.67
    ET
    0.62
     The
    0.59
    TEMP
    0.59
    м
    0.58
    pe
    0.58
     al
    0.57
    ure
    0.56
    anda
    0.56
    POSITIVE LOGITS
    t
    1.37
    p
    0.91
    tails
    0.89
    s
    0.86
    tive
    0.86
    n
    0.86
    g
    0.84
    number
    0.82
    siniz
    0.79
    할
    0.78
    Activations Density 0.045%

    No Known Activations