© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 199559
    Prev
    Next
    INDEX
    Explanations

    numbers in riddles or counting

    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_9_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
    ет
    0.33
    ک
    0.33
    лі
    0.32
    م
    0.31
    ين
    0.31
    い
    0.31
    ﻜ
    0.30
    জ
    0.29
    न
    0.29
    শ
    0.29
    POSITIVE LOGITS
    ’
    0.36
    ra
    0.31
    '
    0.28
     bijection
    0.27
     Bundestag
    0.25
    }%
    0.24
    Plane
    0.24
     Multicolor
    0.24
     Redistributions
    0.24
     Bering
    0.23
    Activations Density 0.009%

    No Known Activations