© 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. 198782
    Prev
    Next
    INDEX
    Explanations

    material deposition process

    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
     bombings
    0.48
     hydrocarbons
    0.47
    asını
    0.46
    ιον
    0.46
    asının
    0.45
    itze
    0.45
    䣷
    0.45
    amble
    0.44
    न्हे
    0.44
    谚
    0.44
    POSITIVE LOGITS
     two
    0.53
     end
    0.50
    IL
    0.50
    4
    0.50
    },
    0.48
     fd
    0.48
    兩
    0.48
     två
    0.48
    _,
    0.47
    県
    0.46
    Activations Density 0.003%

    No Known Activations