© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 84218
    Prev
    Next
    INDEX
    Explanations

    Slack bots, enzymes, aureus, blood clots, fluid

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_23_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
    ⒏
    0.44
     তারাও
    0.42
    🥶
    0.41
    🥴
    0.41
     대체
    0.40
     smtp
    0.40
    Canonical
    0.39
    𝜁
    0.39
    🫢
    0.38
    setMaximum
    0.38
    POSITIVE LOGITS
     says
    0.44
     needs
    0.39
     Neg
    0.39
     seeks
    0.38
     week
    0.38
     ne
    0.37
     huile
    0.37
     has
    0.36
    isy
    0.36
     Belle
    0.36
    Activations Density 0.029%

    No Known Activations