© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 37352
    Prev
    Next
    INDEX
    Explanations

    asking why or how

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
    ahs
    0.50
    "):
    0.44
    ])):
    0.44
    }})\
    0.40
     ae
    0.40
     популација
    0.40
    )):
    0.38
     ys
    0.38
    ").
    0.37
    "]).
    0.37
    POSITIVE LOGITS
     અમને
    0.48
    Our
    0.48
    Get
    0.44
    நம்
    0.44
     recessed
    0.43
    Ἡ
    0.42
     Our
    0.41
     Nuestro
    0.41
    How
    0.40
     наш
    0.40
    Activations Density 0.023%

    No Known Activations