© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 251486
    Prev
    Next
    INDEX
    Explanations

    say "()"

    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_56_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
    —”
    0.38
     लौ
    0.38
    >)</
    0.37
    vodu
    0.36
    }$.)
    0.36
    ​)
    0.36
    ributor
    0.36
    $.)
    0.34
    )}=
    0.34
    Notes
    0.34
    POSITIVE LOGITS
    (
    0.51
    token
    0.49
     instance
    0.49
    instance
    0.48
     token
    0.47
     Token
    0.45
    实例
    0.43
     ||
    0.41
     webhook
    0.40
    TOKEN
    0.40
    Activations Density 0.001%

    No Known Activations