© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106170
    Prev
    Next
    INDEX
    Explanations

    iffusion

    np_acts-logits-general · gemini-2.5-flash-lite

    Riff Method: 4 Reason: The activating texts prominently feature the word "riff" and related concepts in contexts like music (Riffusion, Riffing) and group names (Riffraff)

    np_max-act-logits · gemini-2.5-flash-liteTriggered by @enricobottazzi

    section headers and formatting common in structured AI-generated text.

    oai_token-act-pair · gemini-2.5-flash-liteTriggered by @enricobottazzi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_1_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
    ;
    1.23
    I
    1.11
    !
    1.09
    ing
    1.02
    ди
    1.02
    ру
    1.02
    ق
    0.99
    ке
    0.90
    ?
    0.88
    з
    0.88
    POSITIVE LOGITS
     from
    0.98
     ciekaw
    0.97
    al
    0.96
     zasad
    0.92
    alık
    0.91
     ticaret
    0.91
    các
    0.90
    ון
    0.90
    ငံ
    0.88
     zwią
    0.88
    Activations Density 0.000%

    No Known Activations