© 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. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 196965
    Prev
    Next
    INDEX
    Explanations

    **See below or pics**

    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_26_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
     distinguishable
    0.46
     description
    0.41
    GHz
    0.40
     indist
    0.37
     decomposition
    0.37
     stronger
    0.36
     گوش
    0.36
    (
    0.35
    男
    0.35
    라고
    0.35
    POSITIVE LOGITS
    𝘢
    0.40
     Vigo
    0.38
    媺
    0.38
     बीसीजी
    0.37
     cinci
    0.37
     privado
    0.37
    licted
    0.37
     waahanga
    0.36
     একা
    0.35
     चालीस
    0.35
    Activations Density 0.002%

    No Known Activations