© 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. 139625
    Prev
    Next
    INDEX
    Explanations

    hunter

    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
     हाद
    0.42
    NAD
    0.38
    ancji
    0.37
    汼
    0.37
    NAB
    0.36
    ૮
    0.36
     compressor
    0.36
    ⑷
    0.36
    Portfolio
    0.35
     shipyard
    0.35
    POSITIVE LOGITS
    Tracking
    0.44
     Tracking
    0.43
    tracked
    0.40
    tracking
    0.39
    racted
    0.39
     alam
    0.39
     tracking
    0.38
    urally
    0.37
     직
    0.36
    跟踪
    0.36
    Activations Density 0.001%

    No Known Activations