INDEX

Explanations

a mix of separators, past tense verbs, and words related to data and time

oai_token-act-pair · gemini-2.0-flash

valid

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

antwoorde

-0.47

Vanjske

-0.45

Reprints

-0.41

!*\

-0.41

 recherchez

-0.41

şan

-0.40

Hentet

-0.40

 handled

-0.40

istar

-0.40

homonymie

-0.40

POSITIVE LOGITS

 valid

1.81

 validity

1.76

valid

1.63

 Validity

1.48

validity

1.42

 válido

1.41

Valid

1.39

Validity

1.34

 VALID

1.34

 Valid

1.33

Activations Density 2.861%

a mix of separators, past tense verbs, and words related to data and time

valid

No Comments

No Known Activations