© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 194667
    Prev
    Next
    INDEX
    Explanations

    booking its id

    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_27_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
     yawning
    0.23
    恻
    0.21
     jawa
    0.21
     messing
    0.21
     antagonism
    0.21
     obfusc
    0.20
     कमि
    0.20
     atténuées
    0.20
     mingling
    0.20
     feeling
    0.20
    POSITIVE LOGITS
    坡
    0.20
    米国
    0.20
    denom
    0.19
    ult
    0.19
    虚拟
    0.19
    rh
    0.19
     Afin
    0.18
    therm
    0.18
     basement
    0.18
     Αυ
    0.18
    Activations Density 0.000%

    No Known Activations