© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 169474
    Prev
    Next
    INDEX
    Explanations

    :

    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
    pageToken
    0.42
     ent
    0.42
     u
    0.39
    写
    0.38
    iej
    0.36
     UP
    0.36
     schreibt
    0.35
    urov
    0.35
    ńca
    0.35
    寫
    0.35
    POSITIVE LOGITS
     matters
    0.53
     Matters
    0.43
     matter
    0.42
     Total
    0.42
    ુભ
    0.41
    Matter
    0.40
     Matter
    0.39
    Instructions
    0.38
    стары
    0.38
    做到
    0.38
    Activations Density 0.004%

    No Known Activations