© 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-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8764
    Prev
    Next
    INDEX
    Explanations

    the abbreviation i.e. and words that often occur nearby to it

    oai_token-act-pair · gemini-2.0-flash

    i.e

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.75
     joaat
    -0.72
    లాలు
    -0.66
     مشين
    -0.64
    aarrggbb
    -0.63
    PerformLayout
    -0.62
    ROIT
    -0.62
    óngase
    -0.60
     CURIAM
    -0.60
    
    -0.60
    POSITIVE LOGITS
    notifyListeners
    0.53
    nappropriate
    0.53
    '):
    0.52
    %)$
    0.52
    "):
    0.51
    PDOException
    0.49
    다는
    0.49
    }}_
    0.48
    "):
    0.48
    mbggenerated
    0.47
    Activations Density 2.586%

    No Known Activations