INDEX

Explanations

technical or informative text with terminology specific to a particular domain.

oai_token-act-pair · gemini-2.0-flash

technical parameters and settings

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

idential

-0.49

 eventuali

-0.46

 qualsiasi

-0.45

etate

-0.44

 vaste

-0.44

incre

-0.42

 évent

-0.42

 qualunque

-0.42

berd

-0.41

 permanent

-0.40

POSITIVE LOGITS

///</

0.74

SourceChecksum

0.71

دانشنامهٔ

0.71

исленность

0.69

Geplaatst

0.66

 esternos

0.66

 defaultstate

0.65

AnchorStyles

0.65

 kasarigan

0.65

 MainAxisSize

0.63

Activations Density 17.727%

technical or informative text with terminology specific to a particular domain.

technical parameters and settings

No Comments

No Known Activations