© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 197246
    Prev
    Next
    INDEX
    Explanations

    Abwesenheit und Abschmelzen

    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_4_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
    IS
    0.79
    ை
    0.76
    𝐬
    0.74
    ة
    0.73
    AL
    0.72
    ერ
    0.71
    henyl
    0.70
    ার
    0.69
    nę
    0.67
    ができる
    0.67
    POSITIVE LOGITS
    1
    1.27
    ।
    1.21
    and
    1.20
    на
    1.13
    ad
    1.03
    act
    1.01
    were
    0.98
    aj
    0.93
    $.
    0.92
    t
    0.92
    Activations Density 0.001%

    No Known Activations