© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40509
    Prev
    Next
    INDEX
    Explanations

    light

    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_11_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
    with
    0.62
    Dim
    0.59
    azard
    0.59
    RAND
    0.58
    E
    0.57
    WITH
    0.57
     extinguishing
    0.57
     Před
    0.57
     on
    0.56
    Ext
    0.56
    POSITIVE LOGITS
     $)$.
    0.53
    س
    0.53
     sudah
    0.52
    脷
    0.52
     platter
    0.51
     $)$
    0.51
     conseguir
    0.50
     способны
    0.50
     раст
    0.49
     काबू
    0.49
    Activations Density 0.036%

    No Known Activations