INDEX

Explanations

newspaper titles and reporting verbs

oai_token-act-pair · gemini-2.0-flash

Publications

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 pass

-0.54

Bronnen

-0.43

Kann

-0.43

pass

-0.42

 passes

-0.42

sel

-0.42

 Pass

-0.42

reeg

-0.39

pas

-0.39

熟

-0.39

POSITIVE LOGITS

########.

0.73

tvguidetime

0.72

 iprot

0.68

 betweenstory

0.68

rrggbb

0.66

Personensuche

0.66

 cornice

0.64

 Савезне

0.63

ANTLR

0.63

 ModelRenderer

0.62

Activations Density 1.748%

newspaper titles and reporting verbs

Publications

No Comments

No Known Activations