INDEX

Explanations

people's names, job titles, or affiliations in the document along with pronouns and related conversational connecting words

oai_token-act-pair · gemini-2.0-flash

Legal transcripts/accounts

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

IsMutable

-0.68

principalColumn

-0.57

 Normdatei

-0.52

})();

-0.51

ⓧ

-0.48

RegressionTest

-0.45

 mergeFrom

-0.45

تقاوى

-0.44

[*]

-0.44

 disambiguazione

-0.43

POSITIVE LOGITS

WebVitals

0.80

 виправивши

0.69

AnchorTagHelper

0.63

Portale

0.62

 Egli

0.59

 때문

0.57

DrawerToggle

0.57

 dương

0.57

 itself

0.56

Alike

0.56

Activations Density 34.161%

people's names, job titles, or affiliations in the document along with pronouns and related conversational connecting words

Legal transcripts/accounts

No Comments

No Known Activations