INDEX

Explanations

words and phrases expressing uncertainty or qualification, and language frequently used in legal or official documents.

oai_token-act-pair · gemini-2.0-flash

Subjective descriptions

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

ChildScrollView

-0.60

Hochspringen

-0.60

 Vikipedi

-0.59

verwijspagina

-0.58

 disambiguazione

-0.56

stdc

-0.54

 estekak

-0.54

ismet

-0.54

WebElementEntity

-0.54

fjspx

-0.53

POSITIVE LOGITS

yntaxException

0.59

териалы

0.54

 comigo

0.52

RegressionTest

0.51

 Oyun

0.51

 conmigo

0.50

ne

0.50

مصادر

0.48

Ten

0.47

me

0.47

Activations Density 8.540%

words and phrases expressing uncertainty or qualification, and language frequently used in legal or official documents.

Subjective descriptions

No Comments

No Known Activations