© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 204279
    Prev
    Next
    INDEX
    Explanations

    Learn more

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_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
    (""))
    0.41
    ိုး
    0.38
    }^{+}+\
    0.37
     sermons
    0.36
    CHT
    0.35
    days
    0.34
     ო
    0.34
     riding
    0.34
    ="")
    0.34
    Geschichte
    0.33
    POSITIVE LOGITS
    ссор
    0.42
    proper
    0.42
    ownicy
    0.42
     সঠিক
    0.41
     लिये
    0.41
    要求的
    0.41
     உரிய
    0.38
    覺
    0.38
    ocol
    0.37
    씬
    0.37
    Activations Density 0.002%

    No Known Activations