© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6276
    Prev
    Next
    INDEX
    Explanations

    the fragment "cur" at the beginning of a word

    oai_token-act-pair · gemini-2.0-flash

    cur

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     gyhoeddwyd
    -0.57
    ⓧ
    -0.54
     quæ
    -0.48
    DllImport
    -0.48
    IDTH
    -0.47
    cheri
    -0.46
     quidem
    -0.46
    POSIT
    -0.45
    jublj
    -0.45
    xchange
    -0.45
    POSITIVE LOGITS
     TextAlign
    0.55
    OrNil
    0.54
    cyd
    0.54
    ."]
    0.53
    AxisAlignment
    0.51
    ]")]
    0.51
    llog
    0.50
    קישורים
    0.50
    dios
    0.49
    }];
    0.49
    Activations Density 0.573%

    No Known Activations