INDEX

Explanations

words commonly used when programming

oai_token-act-pair · gemini-2.0-flash

var

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

var

-0.82

tvguidetime

-0.71

var

-0.64

Datuak

-0.64

vare

-0.59

хьтан

-0.59

NameInMap

-0.57

vars

-0.54

VAR

-0.53

 '\\;'

-0.52

POSITIVE LOGITS

marvin

0.57

WireFormatLite

0.56

too

0.52

Ngb

0.51

Comté

0.51

 Haush

0.51

TOO

0.50

längerung

0.49

paign

0.49

вік

0.49

Activations Density 1.376%

words commonly used when programming

var

No Comments

No Known Activations