© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 127337
    Prev
    Next
    INDEX
    Explanations

    serializable `json.dump` Schwartzman

    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_3_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
    I
    0.80
    াস
    0.74
    ai
    0.66
    ною
    0.61
    ρών
    0.61
     воздуха
    0.61
    ะ
    0.60
     पीड़ित
    0.58
    नों
    0.58
    ної
    0.58
    POSITIVE LOGITS
    -
    0.70
    டன்
    0.69
     decentral
    0.63
    n
    0.59
     digit
    0.55
    acken
    0.55
    ut
    0.54
    ly
    0.54
     legitim
    0.54
     ten
    0.52
    Activations Density 0.001%

    No Known Activations