© 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. 3898
    Prev
    Next
    INDEX
    Explanations

    first-person references in the context of recommendations or positive statements.

    oai_token-act-pair · gemini-2.0-flash

    positive testimonials

    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
    RenderAtEndOf
    -0.72
    amerikanische
    -0.63
    __((
    -0.61
    richTextPanel
    -0.58
    rawDesc
    -0.58
     שוליים
    -0.57
     препратки
    -0.57
    RegistryLite
    -0.56
     cherchés
    -0.56
    tvguidetime
    -0.54
    POSITIVE LOGITS
    VersionUID
    0.51
    IARC
    0.51
    umab
    0.49
     absc
    0.48
    jspb
    0.48
    ospor
    0.46
    spoken
    0.45
    oderma
    0.44
    joi
    0.43
    annu
    0.43
    Activations Density 3.457%

    No Known Activations