© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 179540
    Prev
    Next
    INDEX
    Explanations

    removal or cessation

    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_24_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
     Lohia
    0.37
     nain
    0.37
     以
    0.36
     dale
    0.36
     दाल
    0.35
     घी
    0.35
     आंब
    0.35
    ARRIVAL
    0.34
    igueur
    0.34
    ナ
    0.34
    POSITIVE LOGITS
    imų
    0.42
     Keystone
    0.39
    ('.')
    0.39
     Shanghai
    0.38
     molten
    0.38
     Tackle
    0.38
    }]$.
    0.38
     Polish
    0.37
     undocumented
    0.37
    انہ
    0.37
    Activations Density 0.002%

    No Known Activations