© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 107253
    Prev
    Next
    INDEX
    Explanations

    PoC

    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_2_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
     in
    2.05
     to
    1.65
    in
    1.34
     (
    1.13
    ও
    1.11
     incisions
    1.10
     n
    1.09
    ↵
    1.05
     در
    1.05
     I
    0.98
    POSITIVE LOGITS
    _
    1.60
    p
    1.20
    ти
    1.09
    File
    1.08
    ä
    1.08
    Prova
    1.02
    c
    1.01
     Retour
    1.00
    phed
    0.99
    \%
    0.98
    Activations Density 0.004%

    No Known Activations