© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110046
    Prev
    Next
    INDEX
    Explanations

    song title

    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
    _
    1.55
    1
    1.43
     as
    1.34
     않았
    1.24
     중요
    1.23
     сообщи
    1.14
     має
    1.11
    える
    1.09
     οποίο
    1.09
     했
    1.08
    POSITIVE LOGITS
    d
    1.55
    g
    1.46
    in
    1.40
    ou
    1.20
    i
    1.14
    ۰
    1.14
    er
    1.13
    re
    1.07
    z
    1.07
    u
    1.06
    Activations Density 0.001%

    No Known Activations