© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 80441
    Prev
    Next
    INDEX
    Explanations

    Node.js require statements

    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_31_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
    コー
    0.18
    mbito
    0.16
    Cargo
    0.16
    Styl
    0.15
    Inn
    0.15
    Deterministic
    0.15
    璟
    0.15
    内
    0.15
    ])),
    0.14
     करवाते
    0.14
    POSITIVE LOGITS
     sequences
    0.16
    sequences
    0.15
    isTrack
    0.15
     discourses
    0.14
     دان
    0.14
     paprika
    0.14
     samos
    0.14
     fixer
    0.14
     debacle
    0.14
     parab
    0.14
    Activations Density 0.000%

    No Known Activations