© 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. 3974
    Prev
    Next
    INDEX
    Explanations

    individual words, numbers, letters, or punctuation with values 10, 9, or 8

    oai_token-act-pair · gemini-2.0-flash

    in

    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
     Efq
    -0.53
     Theſe
    -0.51
     itſelf
    -0.46
     Monfieur
    -0.45
     myſelf
    -0.38
    <bos>
    -0.35
     Jefus
    -0.35
     becauſe
    -0.34
     varandra
    -0.33
     himſelf
    -0.32
    POSITIVE LOGITS
    rungsseite
    1.03
    
    0.96
     utafitiHapana
    0.96
     nahilalakip
    0.94
     the
    0.93
    ंदीखरीदारी
    0.93
    4
    0.93
    expandindo
    0.92
     Mark
    0.91
     CanadaChoose
    0.91
    Activations Density 75.364%

    No Known Activations