© 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. 8989
    Prev
    Next
    INDEX
    Explanations

    words related to the general topic of positive influence or affect.

    oai_token-act-pair · gemini-2.0-flash

    win

    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
    Her
    -2.25
     Her
    -2.16
    She
    -2.05
     She
    -1.95
    her
    -1.90
     her
    -1.73
    she
    -1.63
     HER
    -1.45
    HER
    -1.44
     she
    -1.38
    POSITIVE LOGITS
     CreateTagHelper
    0.89
    SourceChecksum
    0.80
    DeleteBehavior
    0.79
     here
    0.78
    contentLoaded
    0.76
     dAtA
    0.76
    !*\
    0.75
    WithIOException
    0.75
     estekak
    0.74
     <=",
    0.74
    Activations Density 5.170%

    No Known Activations