© 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. 251825
    Prev
    Next
    INDEX
    Explanations

    introducing lists

    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
     man
    0.57
     shown
    0.47
    Shown
    0.46
    +:
    0.45
    ):
    0.44
    :$
    0.44
     Shown
    0.42
     Man
    0.42
    )—
    0.41
    :
    0.41
    POSITIVE LOGITS
    ưởng
    0.36
     échanc
    0.36
     '.';
    0.35
    igenza
    0.35
     pédicule
    0.35
     다음과
    0.34
    ('').
    0.34
    Zr
    0.33
     (“
    0.33
    dü
    0.32
    Activations Density 0.012%

    No Known Activations