INDEX

Explanations

words about assigning fault or negligence

oai_token-act-pair · gemini-2.0-flash

culpability

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

StoryboardSegue

-0.91

tagHelperRunner

-0.75

 يتيمه

-0.64

WebVitals

-0.64

MessageOf

-0.60

ValueStyle

-0.58

IntoConstraints

-0.58

NewUrlParser

-0.58

:+:

-0.53

Datuak

-0.53

POSITIVE LOGITS

Blame

0.60

 blame

0.60

 Blame

0.53

blame

0.50

KEYCODE

0.47

perm

0.47

ηγ

0.47

kheim

0.46

 blaming

0.46

 fault

0.46

Activations Density 2.154%

words about assigning fault or negligence

culpability

No Comments

No Known Activations