INDEX

Explanations

code syntax, likely identifying the start or end of code blocks or structures

oai_token-act-pair · gemini-2.0-flash

}

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 onOptions

-0.57

reportWebVitals

-0.56

Portail

-0.54

Еще

-0.53

PropertyGroup

-0.53

ITECH

-0.52

 endblock

-0.51

íí

-0.51

AccessorTable

-0.50

BrowserModule

-0.49

POSITIVE LOGITS

AndEndTag

0.82

ുക

0.50

KURZBESCHREIBUNG

0.50

bewerken

0.49

تقاوى

0.48

})$}

0.47

 Sili

0.47

PhysRevD

0.46

 comuniques

0.46

 data

0.46

Activations Density 1.704%

code syntax, likely identifying the start or end of code blocks or structures

}

No Comments

No Known Activations