© 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. 5744
    Prev
    Next
    INDEX
    Explanations

    adjectives related to suitability and timeliness

    oai_token-act-pair · gemini-2.0-flash

    ways or characteristics

    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
     dropped
    -0.82
     dropping
    -0.75
     fashion
    -0.75
     drop
    -0.71
     Drop
    -0.68
    Drop
    -0.67
    fashion
    -0.66
    Fashion
    -0.64
     Fashion
    -0.63
    drop
    -0.63
    POSITIVE LOGITS
     Efq
    1.05
     myſelf
    1.05
     itſelf
    1.02
     houſe
    1.02
     متعلقه
    1.01
     Theſe
    1.01
     Monfieur
    0.98
     pleaſure
    0.98
     ―――――
    0.93
     Houſe
    0.93
    Activations Density 7.315%

    No Known Activations