© 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. 206155
    Prev
    Next
    INDEX
    Explanations

    Objects and things

    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
     play
    0.48
     start
    0.41
    play
    0.41
     face
    0.39
    Ғ
    0.36
    Face
    0.36
    chwitz
    0.35
    flächen
    0.35
     puch
    0.35
     кош
    0.34
    POSITIVE LOGITS
     near
    0.54
    NEAR
    0.50
    near
    0.50
     Near
    0.46
     proximate
    0.46
    Near
    0.46
     열
    0.45
     NEAR
    0.45
     nearer
    0.42
     gần
    0.41
    Activations Density 0.002%

    No Known Activations