© 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. 824
    Prev
    Next
    INDEX
    Explanations

    mentions of purchasing or making craft cards, especially baby-themed cards with decorative items, potentially within a sales context.

    oai_token-act-pair · gemini-2.0-flash

    card making blogs

    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
    TagMode
    -0.70
    aarrggbb
    -0.67
    Tikang
    -0.65
    tagHelperRunner
    -0.64
    EndGlobalSection
    -0.62
    istoitu
    -0.61
    HomeAsUpEnabled
    -0.60
    ResponseWriter
    -0.59
    +#+#
    -0.58
     мәкалә
    -0.57
    POSITIVE LOGITS
    Mobile
    0.48
    </tbody>
    0.45
    rinth
    0.44
    이션
    0.44
     []:
    0.43
     Mobile
    0.43
     aapt
    0.43
     mobile
    0.43
    FMC
    0.42
     bush
    0.42
    Activations Density 7.204%

    No Known Activations