© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 25511
    Prev
    Next
    INDEX
    Explanations

    how to force install

    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_10_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
    0
    0.28
    4
    0.27
    5
    0.26
    2
    0.25
    1
    0.24
    AN
    0.24
     genug
    0.23
    }
    0.23
    3
    0.23
     gyda
    0.23
    POSITIVE LOGITS
    ل
    0.24
    ями
    0.23
    л
    0.22
    روں
    0.21
    ଁ
    0.21
     то
    0.21
    anın
    0.21
    ẩ
    0.21
    가의
    0.21
     탱크
    0.20
    Activations Density 0.169%

    No Known Activations