© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4337
    Prev
    Next
    INDEX
    Explanations

    text referring to a person or people creating or building something as a project, perhaps a squad of figurines.

    oai_token-act-pair · gemini-2.0-flash

    War/military context

    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
    AndEndTag
    -0.82
    bootstrapcdn
    -0.78
    SPATH
    -0.78
    LookAnd
    -0.71
    ftagPool
    -0.70
    esModule
    -0.69
    tagHelperRunner
    -0.67
     елның
    -0.64
    Rohy
    -0.63
    ThroughAttribute
    -0.62
    POSITIVE LOGITS
     Charms
    0.50
    geist
    0.48
    brave
    0.47
     Disciples
    0.47
     motif
    0.46
    initialization
    0.44
    deling
    0.44
     BRIG
    0.43
    urgia
    0.43
    ירים
    0.43
    Activations Density 6.930%

    No Known Activations