INDEX

Explanations

topics discussed in academic articles or philosophical arguments

oai_token-act-pair · gemini-2.0-flash

Ways of doing/describing

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

 Monfieur

-0.68

 ſtate

-0.68

 pleaſure

-0.65

 Jefus

-0.64

 houſe

-0.63

 ftate

-0.61

 Diſ

-0.56

 diſt

-0.56

 auffi

-0.56

 beſt

-0.56

POSITIVE LOGITS

CodeAttribute

0.71

<bos>

0.71

postIndex

0.66

 <=",

0.66

таратура

0.59

encodeWith

0.58

 ModelExpression

0.57

SourceChecksum

0.56

DoubleQuotes

0.56

ⓧ

0.56

Activations Density 56.826%

topics discussed in academic articles or philosophical arguments

Ways of doing/describing

No Comments

No Known Activations