© 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. 6863
    Prev
    Next
    INDEX
    Explanations

    nouns and adjectives describing clothing

    oai_token-act-pair · gemini-2.0-flash

    modifications

    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
    RunAsync
    -0.56
     auroit
    -0.53
    webElement
    -0.52
     TÉCN
    -0.52
    Nuorodos
    -0.51
     pioggia
    -0.50
     roulant
    -0.50
     Technical
    -0.49
    autorité
    -0.49
    enschutz
    -0.49
    POSITIVE LOGITS
    Diweddarwch
    0.61
    #+#
    0.60
    MemoryWarning
    0.51
    providedIn
    0.48
    EnableWeb
    0.47
    InlineData
    0.47
    bcryptjs
    0.46
    IsContent
    0.46
     jScrollPane
    0.45
    <()>
    0.44
    Activations Density 8.556%

    No Known Activations