INDEX

Explanations

code

np_token-act-pair-logits · gemini-2.0-flash

code blocks or indentations

oai_token-act-pair · gemini-2.0-flash

Code snippets

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 CommonModule

-0.75

verwijspagina

-0.56

EDEFAULT

-0.54

SourceChecksum

-0.53

tagHelperRunner

-0.51

NameInMap

-0.51

NewRow

-0.49

Kij

-0.48

DataSetChanged

-0.46

ificantly

-0.46

POSITIVE LOGITS

:✨

0.69

putan

0.65

+#+

0.58

 كومونز

0.55

archiviato

0.54

 betweenstory

0.53

 beginnetje

0.52

 insu

0.51

uguetes

0.51

 dome

0.50

Activations Density 0.451%

code

code blocks or indentations

Code snippets

No Comments

No Known Activations