© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 60309
    Prev
    Next
    INDEX
    Explanations

    did not have

    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
    ка
    1.16
    ’
    1.11
    ,
    0.99
     tony
    0.93
    ن
    0.91
     foodie
    0.91
    信息
    0.90
     pomoc
    0.90
    做
    0.89
    誢
    0.88
    POSITIVE LOGITS
    were
    2.02
    to
    1.40
    0
    1.36
    ０
    1.27
    will
    1.22
    was
    1.17
    u
    1.14
    with
    1.13
    та
    1.12
    would
    1.10
    Activations Density 0.000%

    No Known Activations