© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 21345
    Prev
    Next
    INDEX
    Explanations

    implementation

    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
    "/><
    0.39
    ';"/>
    0.37
    μοι
    0.37
    ']],
    0.37
    ’?
    0.36
    ’”
    0.36
    '_
    0.36
    sheep
    0.36
    ...”
    0.36
    முகச்
    0.36
    POSITIVE LOGITS
    ("
    0.46
    亦
    0.41
    }(\
    0.40
     ("
    0.40
    (
    0.39
     Works
    0.39
     WORKS
    0.38
     SUCH
    0.38
    utilise
    0.37
     works
    0.37
    Activations Density 0.000%

    No Known Activations