© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 9096
    Prev
    Next
    INDEX
    Explanations

    docstring start """

    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_40_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
    +)$
    0.37
    сть
    0.35
    ')['
    0.35
    })+
    0.35
    陌生
    0.34
    uffy
    0.34
     Absorption
    0.34
    ضای
    0.34
    किस्तान
    0.33
    ])+
    0.33
    POSITIVE LOGITS
     self
    0.61
     Self
    0.54
    Self
    0.53
    self
    0.52
     Selbst
    0.48
     assertions
    0.46
     सेल्फ
    0.46
     SELF
    0.45
    Though
    0.44
     asserting
    0.43
    Activations Density 0.019%

    No Known Activations