© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 210991
    Prev
    Next
    INDEX
    Explanations

    matchbox

    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_5_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
    ни
    1.48
    та
    1.30
    ა
    1.21
    τές
    1.18
    ло
    1.17
    स्ट
    1.09
    룺
    1.09
    тва
    1.08
    талия
    1.07
    поте
    1.05
    POSITIVE LOGITS
    man
    1.33
    for
    1.10
    it
    1.05
    with
    1.05
    if
    1.02
    ice
    1.01
     It
    0.98
    3
    0.96
    ،
    0.96
    ow
    0.95
    Activations Density 0.000%

    No Known Activations