© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 104092
    Prev
    Next
    INDEX
    Explanations

    say numbers

    np_max-act-logits · gemini-2.5-flash-lite

    words related to explosives or bombing.

    oai_token-act-pair · gemini-2.5-flash-liteTriggered by @enricobottazzi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
     Boucher
    0.40
     ద
    0.39
    Dropped
    0.39
    Conn
    0.38
     vui
    0.37
    殒
    0.37
    czenia
    0.36
     என்ன
    0.35
    /'+
    0.35
     ग्राफ
    0.35
    POSITIVE LOGITS
     Forty
    0.40
     अखंड
    0.39
    PREFIX
    0.39
    ⌦
    0.38
     VIDA
    0.38
     १८
    0.37
     prefixes
    0.36
     forty
    0.36
     displayText
    0.36
     ১৩২২
    0.35
    Activations Density 0.030%

    No Known Activations