Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 19-GEMMASCOPE-TRANSCODER-16K
    4. 9973
    Prev
    Next
    INDEX
    Explanations

    mentions of isolation and leaving.

    oai_token-act-pair · gemini-2.0-flash

    alone

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    Chham
    -0.72
    AnchorStyles
    -0.70
    帖最后由
    -0.69
    دانشنامهٔ
    -0.68
     pinulongan
    -0.66
    RUnlock
    -0.65
    HasForeignKey
    -0.65
    tagHelperRunner
    -0.62
    MigrationBuilder
    -0.61
    ISupport
    -0.59
    POSITIVE LOGITS
    自己在
    0.52
    endiri
    0.51
    自己
    0.49
    alone
    0.49
     alone
    0.48
    aulted
    0.47
     Alone
    0.46
     m
    0.45
    csol
    0.45
    ี่ยว
    0.45
    Activations Density 0.803%

    No Known Activations