INDEX

Explanations

scientific language describing the reaction of cells to external forces

oai_token-act-pair · gemini-2.0-flash

flexibility

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

 podjela

-0.50

hau

-0.47

Lor

-0.46

coff

-0.46

 Teufel

-0.45

❤❤

-0.44

 annot

-0.44

UseVisualStyle

-0.44

intahan

-0.44

setArguments

-0.44

POSITIVE LOGITS

 flexibility

1.12

Flexibility

0.98

 Flexibility

0.98

 flexible

0.91

 flexib

0.90

 stability

0.89

flex

0.84

 agility

0.83

 FLEX

0.82

elastic

0.81

Activations Density 2.206%

scientific language describing the reaction of cells to external forces

flexibility

No Comments

No Known Activations