© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 7809
    Prev
    Next
    INDEX
    Explanations

    numbers and list elements

    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_40_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
    th
    0.63
    โมง
    0.56
    वीं
    0.55
    ths
    0.44
     mieux
    0.43
    월
    0.42
    десят
    0.41
    thand
    0.41
    zig
    0.40
    цията
    0.38
    POSITIVE LOGITS
    性和
    0.40
     ১৫০
    0.39
     multipliers
    0.36
     Espero
    0.36
    }=(\
    0.35
    ListenAnd
    0.34
    PickerDialog
    0.33
     travellers
    0.33
    三百
    0.33
     Así
    0.33
    Activations Density 0.121%

    No Known Activations