© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 21115
    Prev
    Next
    INDEX
    Explanations

    air

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    SHA
    0.42
     SHA
    0.41
    ня
    0.40
    aried
    0.40
    샤
    0.39
    shaw
    0.39
    sha
    0.39
    עד
    0.38
    ធី
    0.38
    onta
    0.38
    POSITIVE LOGITS
    𝚒
    0.39
    gano
    0.39
     интере
    0.38
    quee
    0.38
    ول
    0.38
     LaF
    0.38
    bi
    0.38
    barer
    0.38
     OL
    0.37
     Seren
    0.37
    Activations Density 0.006%

    No Known Activations