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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15961
    Prev
    Next
    INDEX
    Explanations

    mentions of "fine-tuning"

    oai_token-act-pair · gemini-2.0-flash

    fine applications

    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
     fine
    -3.31
    Fine
    -3.16
    fine
    -3.08
     Fine
    -3.08
     FINE
    -2.89
    FINE
    -2.50
     finer
    -2.30
     fines
    -1.91
    fines
    -1.83
     finely
    -1.77
    POSITIVE LOGITS
     quæ
    0.59
     Latimer
    0.55
    occasione
    0.52
     composizione
    0.50
     eorum
    0.49
    JAXB
    0.49
     spedizione
    0.48
     omnes
    0.48
     cioccolato
    0.47
     tibi
    0.46
    Activations Density 2.229%

    No Known Activations