© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144516
    Prev
    Next
    INDEX
    Explanations

    casters

    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_0_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
    "
    2.11
    ?
    1.45
    ك
    1.39
    غ
    1.16
    )
    1.16
    “
    1.16
    }
    1.15
    أ
    1.14
    "*
    1.12
    2
    1.12
    POSITIVE LOGITS
    る
    1.43
    al
    1.37
     (
    1.34
    el
    1.30
     jonka
    1.26
    larni
    1.20
    ١
    1.16
     않았
    1.14
    ों
    1.13
     არის
    1.13
    Activations Density 0.000%

    No Known Activations