INDEX

Explanations

names of people and honorifics

oai_token-act-pair · gemini-2.0-flash

names in dialogue

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

UserScript

-0.73

KURZBESCHREIBUNG

-0.68

IsContent

-0.63

AnchorTagHelper

-0.60

romptu

-0.60

LookAnd

-0.60

versaire

-0.60

 purpoſe

-0.59

 fubject

-0.59

 Normdatei

-0.58

POSITIVE LOGITS

 autorytatywna

0.53

IntoConstraints

0.47

ature

0.43

series

0.42

MUM

0.42

 fadeIn

0.41

material

0.40

매

0.40

în

0.40

ētu

0.39

Activations Density 4.401%

names of people and honorifics

names in dialogue

No Comments

No Known Activations