© 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. 250412
    Prev
    Next
    INDEX
    Explanations

    accented characters

    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
    will
    0.29
    let
    0.28
     pyperclip
    0.27
    ceria
    0.25
     hasten
    0.25
    }}}}$
    0.25
     locate
    0.24
    LET
    0.24
    හාර
    0.24
    将
    0.24
    POSITIVE LOGITS
    á
    0.53
    ão
    0.52
    ait
    0.40
    à
    0.38
    emos
    0.38
    anno
    0.37
    ÃO
    0.36
    ont
    0.36
    án
    0.35
    ás
    0.34
    Activations Density 0.001%

    No Known Activations