© 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. 107282
    Prev
    Next
    INDEX
    Explanations

    Theo Faber, Nyquist Frequency

    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
    h
    1.40
    t
    1.29
    v
    1.16
    ld
    1.09
    ون
    1.07
    f
    1.03
    ru
    1.01
    er
    0.98
    le
    0.97
    í
    0.97
    POSITIVE LOGITS
    ה
    1.36
    も
    1.33
    𝙖
    1.32
    '
    1.30
    도
    1.30
     têm
    1.25
    ă
    1.25
     possono
    1.14
    ও
    1.13
     kerana
    1.13
    Activations Density 0.000%

    No Known Activations