INDEX

Explanations

code snippets with explanations, possibly in a different language

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_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

Publica

-0.45

ẾT

-0.45

DispatchToProps

-0.42

estries

-0.42

erdings

-0.41

PTP

-0.40

ettbewerb

-0.39

ρεί

-0.38

Всего

-0.38

ędzy

-0.38

POSITIVE LOGITS

ValueStyle

0.77

SourceChecksum

0.68

WebVitals

0.68

 AssemblyCulture

0.64

BufferException

0.62

}{@

0.60

JpaRepository

0.57

WEBPACK

0.57

 doInBackground

0.57

клопе

0.56

Activations Density 0.493%

code snippets with explanations, possibly in a different language

Code snippets

No Comments

No Known Activations