© 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-3-4B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-16K
    7. 53
    Prev
    Next
    INDEX
    Explanations

    comparative language and analogies used to explain or relate one concept to another.

    oai_token-act-pair · claude-4-5-haikuTriggered by @ruq2026

    comparisons

    np_max-act · gemini-2.5-flash-liteTriggered by @ruq2026
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_12_width_16k_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
     THIS
    0.23
    /
    0.19
     this
    0.19
     wife
    0.19
     ikke
    0.19
     questa
    0.18
     STUDENTS
    0.18
     angered
    0.18
     volta
    0.18
     til
    0.18
    POSITIVE LOGITS
    UInt
    0.16
     अपेक्षा
    0.16
    enswert
    0.16
    獎
    0.16
    Requirement
    0.16
    extrémité
    0.16
    ያስ
    0.16
    éu
    0.15
     ادی
    0.15
    requirements
    0.15
    Activations Density 0.919%

    No Known Activations