© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2088
    Prev
    Next
    INDEX
    Explanations

    film critiques that use subjective words to express negative critical opinions, often about satire or humor

    oai_token-act-pair · gemini-2.0-flash

    Media reviews

    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
    Personensuche
    -0.59
    zeera
    -0.55
    ibatis
    -0.52
    匪
    -0.50
    ArrowToggle
    -0.50
    はじめに
    -0.49
    GENERIC
    -0.47
     cheesy
    -0.46
    कल
    -0.46
    Спољашње
    -0.45
    POSITIVE LOGITS
    ClCompile
    0.66
    󠁣
    0.59
     législation
    0.57
    yntaxException
    0.53
    ErrUnexpectedEOF
    0.52
    principalTable
    0.52
    ohistochemistry
    0.52
     contextLoads
    0.51
    θρω
    0.51
     ©️
    0.51
    Activations Density 5.780%

    No Known Activations