© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261432
    Prev
    Next
    INDEX
    Explanations

    shareware, freeware, spyware, software

    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_5_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
     as
    1.78
    u
    1.51
    प
    1.44
    as
    1.27
    ل
    1.26
    其他
    1.25
    ב
    1.25
    મ
    1.24
    ب
    1.23
    to
    1.22
    POSITIVE LOGITS
    。
    1.65
    <0x93>
    1.35
    <0xA4>
    1.30
    <0xAC>
    1.23
    <0xBC>
    1.21
    )
    1.21
    ۔
    1.21
    ።
    1.20
    <0xBE>
    1.18
    ),
    1.17
    Activations Density 0.000%

    No Known Activations