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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 167535
    Prev
    Next
    INDEX
    Explanations

    late/included

    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
    depending
    0.40
    >');
    0.40
    }));
    0.40
    )}(\
    0.39
    कप्तान
    0.39
    Eg
    0.38
     இயந்திர
    0.36
    dims
    0.36
    )([
    0.35
    ])]
    0.35
    POSITIVE LOGITS
     late
    0.67
     Late
    0.60
     Included
    0.55
     included
    0.55
     Ca
    0.54
    Late
    0.50
     ca
    0.50
    Included
    0.49
    included
    0.48
     Pl
    0.47
    Activations Density 0.006%

    No Known Activations