INDEX

Explanations

code markup symbols in different languages

oai_token-act-pair · gemini-2.0-flash

code

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 AssemblyCulture

-0.89

TagMode

-0.80

 autorytatywna

-0.79

QMetaType

-0.76

RectangleBorder

-0.74

awtextra

-0.73

 Majefty

-0.73

Jegyzetek

-0.72

TintMode

-0.71

 faſt

-0.71

POSITIVE LOGITS

omite

0.48

<eos>

0.46

0.44

}")

0.42

↵

0.41

↵↵↵

0.39

ate

0.37

 חיצוניים

0.37

↵↵↵↵↵↵↵

0.36

 Original

0.35

Activations Density 5.958%

code markup symbols in different languages

code

No Comments

No Known Activations