© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 178552
    Prev
    Next
    INDEX
    Explanations

    example path commands

    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_24_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
    BURTS
    0.43
    StoredKeys
    0.42
     decking
    0.42
    颳
    0.42
    হইয়া
    0.41
    كنولوجيا
    0.40
    ানুভূতি
    0.40
    THAN
    0.40
    មុខ
    0.40
    }^{*}-
    0.40
    POSITIVE LOGITS
     since
    0.48
     \
    0.48
     RHS
    0.41
     block
    0.40
     Increase
    0.40
     rel
    0.40
    7
    0.40
     from
    0.40
     comm
    0.40
     usp
    0.40
    Activations Density 0.007%

    No Known Activations