© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 203209
    Prev
    Next
    INDEX
    Explanations

    HTML entities and tags

    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_12_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
     MILLER
    0.25
    )
    0.22
     Re
    0.20
    ા
    0.20
     Miller
    0.19
    ે
    0.19
    }
    0.19
     scorsa
    0.19
     awarded
    0.19
     conceded
    0.19
    POSITIVE LOGITS
    Wings
    0.25
    t
    0.21
    Sig
    0.20
    Rome
    0.20
    Airplane
    0.20
    Pat
    0.20
    জীবন
    0.20
    Hue
    0.20
    Regression
    0.19
    Bismillahirrah
    0.19
    Activations Density 0.001%

    No Known Activations