© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 163294
    Prev
    Next
    INDEX
    Explanations

    pushing off

    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_31_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
     coveredmethods
    0.44
    Recording
    0.44
     Recording
    0.43
     DISEASE
    0.42
     devastating
    0.40
     Disease
    0.40
     தொற்று
    0.39
    峈
    0.38
     desapare
    0.38
     decim
    0.38
    POSITIVE LOGITS
    ilit
    0.35
     પ્રાપ્ત
    0.35
     इत
    0.35
     induc
    0.35
    payload
    0.35
     rigidly
    0.35
    hydro
    0.34
    垂
    0.34
    plasma
    0.34
     kull
    0.33
    Activations Density 0.001%

    No Known Activations