© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 235149
    Prev
    Next
    INDEX
    Explanations

    anyMethod: 1Reason: MAX_ACTIVATING_TOKENS are all the same token

    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_46_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
    特
    0.44
    quine
    0.38
     получа
    0.37
     січня
    0.36
    ChangeListener
    0.36
    forget
    0.35
    íes
    0.35
    mic
    0.35
    schild
    0.35
    testing
    0.35
    POSITIVE LOGITS
     Amongst
    0.40
     Scheduled
    0.38
     scanty
    0.38
     MEC
    0.37
     প্রক্রিয়াধীন
    0.36
    뉩
    0.36
     oily
    0.36
    UpInside
    0.36
    andoah
    0.35
     MANY
    0.35
    Activations Density 0.003%

    No Known Activations