© 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. 12955
    Prev
    Next
    INDEX
    Explanations

    vague positive terms and terms related to rules and laws

    oai_token-act-pair · gemini-2.0-flash

    very

    np_max-act · gemini-2.0-flash

    very

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     OFDb
    -0.65
     tartalomajánló
    -0.64
    ourites
    -0.64
    })->
    -0.60
    HOUT
    -0.56
    рито
    -0.54
    CIR
    -0.53
    Spoljašnje
    -0.53
    rachtet
    -0.52
    endlich
    -0.52
    POSITIVE LOGITS
    ].)
    0.69
    Mengapa
    0.69
     cuja
    0.68
    Cuáles
    0.67
    ?
    0.65
     cuyos
    0.62
    örté
    0.61
     isolato
    0.61
     cuyas
    0.60
     credere
    0.59
    Activations Density 1.473%

    No Known Activations