© 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. 8591
    Prev
    Next
    INDEX
    Explanations

    text related to self-help tips and writing strategies

    oai_token-act-pair · gemini-2.0-flash

    foreign language

    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
     defaultstate
    -0.79
    contentLoaded
    -0.76
    SourceChecksum
    -0.72
    MessageOf
    -0.67
    DockStyle
    -0.66
    parsedMessage
    -0.65
     gynhyrchwyd
    -0.59
    StructEnd
    -0.57
    ">//
    -0.53
    jsonwebtoken
    -0.50
    POSITIVE LOGITS
     vectorielle
    0.57
     minOccurs
    0.52
     nemlig
    0.52
     giả
    0.50
    DebuggerStep
    0.50
     hilos
    0.47
    ciptakan
    0.47
     espectáculos
    0.47
     quirúrg
    0.47
     Globals
    0.46
    Activations Density 9.521%

    No Known Activations