INDEX

Explanations

a mix of code-related terms and references to UI elements or data manipulation

oai_token-act-pair · gemini-2.0-flash

code/errors

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

 pulmonar

-0.58

 herbic

-0.57

 Brasília

-0.56

 terapé

-0.54

 barbati

-0.53

 بيها

-0.52

 autorisation

-0.52

tvguidetime

-0.52

feitura

-0.51

seamnă

-0.51

POSITIVE LOGITS

tagHelperRunner

0.61

findpost

0.60

Билгалдахарш

0.59

AutoField

0.57

(!__

0.54

TagHelper

0.51

 WebDriverWait

0.51

TProtocol

0.50

fjspx

0.49

 ***!

0.49

Activations Density 7.242%

a mix of code-related terms and references to UI elements or data manipulation

code/errors

No Comments

No Known Activations