© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 228824
    Prev
    Next
    INDEX
    Explanations

    extra limbs

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
     member
    0.42
    member
    0.42
    ד
    0.41
    woman
    0.40
     age
    0.38
    uzione
    0.37
     organisé
    0.37
     мужчина
    0.37
    deki
    0.36
    rino
    0.36
    POSITIVE LOGITS
    ὀ
    0.40
    իտ
    0.39
    িত
    0.38
     calmodulin
    0.37
    過了
    0.37
    阿拉
    0.37
    onda
    0.36
    JAV
    0.36
    ॉन्स
    0.36
     Dijk
    0.36
    Activations Density 0.001%

    No Known Activations