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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 3664
    Prev
    Next
    INDEX
    Explanations

    references to a female character's physical reactions or body, particularly in the context of romance or heightened emotion

    oai_token-act-pair · gemini-2.0-flash

    fictional stories

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    LookAnd
    -0.69
    principalColumn
    -0.68
     BoxFit
    -0.68
     nakalista
    -0.67
     Lightboxes
    -0.67
    verwijspagina
    -0.65
     незавершена
    -0.64
    ngdoc
    -0.64
     '\\;'
    -0.64
    новништво
    -0.63
    POSITIVE LOGITS
    ">//
    0.50
    ष्ठ
    0.46
     un
    0.46
    Un
    0.44
     Schiller
    0.44
     *)__
    0.44
    λή
    0.43
    }();
    0.43
    unci
    0.42
     une
    0.42
    Activations Density 1.527%

    No Known Activations