INDEX

Explanations

lines starting with at least one space followed by an asterisk, and also lines containing `@param` or `@return`.

oai_token-act-pair · gemini-2.0-flash

@

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 estekak

-1.16

 AssemblyProduct

-1.05

tvguidetime

-0.94

 surla

-0.91

 дописавши

-0.91

rungsseite

-0.87

 snippetHide

-0.85

Filmografia

-0.82

 Roskov

-0.82

 المعيارى

-0.79

POSITIVE LOGITS

fe

0.49

nel

0.45

come

0.42

wo

0.42

 precum

0.42

COME

0.42

return

0.41

ke

0.41

orn

0.41

Return

0.41

Activations Density 0.367%

lines starting with at least one space followed by an asterisk, and also lines containing `@param` or `@return`.

@

No Comments

No Known Activations