© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 141882
    Prev
    Next
    INDEX
    Explanations

    requesting citations

    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_0_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
    ，
    1.27
     drugih
    1.23
     cikin
    1.13
     wasn
    1.11
     brows
    1.11
    𝟎
    1.11
     regista
    1.09
     critic
    1.09
     negligent
    1.09
     Piaget
    1.09
    POSITIVE LOGITS
    .
    1.44
    and
    1.41
    ř
    1.34
    ál
    1.32
    able
    1.30
    old
    1.30
    п
    1.29
    ud
    1.23
    ذ
    1.23
     on
    1.22
    Activations Density 0.000%

    No Known Activations