© 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. 22412
    Prev
    Next
    INDEX
    Explanations

    abstract concepts

    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
    更好
    0.47
     am
    0.46
    怯
    0.39
     thin
    0.39
     aberr
    0.37
     aberrant
    0.37
     pratic
    0.36
     spurious
    0.35
     sane
    0.35
     tame
    0.35
    POSITIVE LOGITS
    }))$
    0.41
     Croatia
    0.41
     ]))
    0.39
     යු
    0.39
     Plate
    0.39
    orca
    0.38
     Еўро
    0.38
    }}(\
    0.38
     Type
    0.38
    rugula
    0.38
    Activations Density 0.002%

    No Known Activations