© 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. 107476
    Prev
    Next
    INDEX
    Explanations

    scion / ion / ions

    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
    (
    1.46
    ).
    1.35
    (.*
    1.20
    <0x80>
    1.15
    _
    1.15
    (?:
    1.13
    かと
    1.05
    ับ
    1.03
     Влади
    1.02
    '
    1.02
    POSITIVE LOGITS
    in
    1.67
    el
    1.46
    ent
    1.41
    al
    1.41
    ies
    1.39
    ur
    1.35
    as
    1.33
    ia
    1.32
    are
    1.27
    io
    1.26
    Activations Density 0.001%

    No Known Activations