© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4892
    Prev
    Next
    INDEX
    Explanations

    statements of fact or plausibility in opinions, reports, or historical accounts.

    oai_token-act-pair · gemini-2.0-flash

    truth and clarity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    providedIn
    -0.79
     okuyayım
    -0.77
     متعلقه
    -0.72
    évaluateur
    -0.72
     Paglinawan
    -0.66
     Roskov
    -0.65
     protoimpl
    -0.65
     оригіналу
    -0.60
     Оно
    -0.58
    archiviato
    -0.56
    POSITIVE LOGITS
    <bos>
    0.66
     realised
    0.63
    יצד
    0.59
     realise
    0.56
     clamour
    0.55
     enquired
    0.54
     speculate
    0.53
     realising
    0.52
    θος
    0.52
     ascertained
    0.51
    Activations Density 1.794%

    No Known Activations