INDEX

Explanations

code snippets that contain references to processes, function calls, and memory management.

oai_token-act-pair · gemini-2.0-flash

code context

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

 Himo

-0.64

醐

-0.60

Hentet

-0.60

 propOrder

-0.56

();)

-0.54

URLException

-0.54

 Wikispecies

-0.54

)))));

-0.50

Datuak

-0.50

thâu

-0.50

POSITIVE LOGITS

Diweddarwch

0.58

 blocks

0.57

 Blocks

0.55

UnknownFieldSet

0.54

 findBy

0.54

blocks

0.48

 Block

0.48

וויק

0.48

 swims

0.48

 itemprop

0.47

Activations Density 6.320%

code snippets that contain references to processes, function calls, and memory management.

code context

No Comments

No Known Activations