INDEX

Explanations

the abbreviation "V" followed by zero to two more letters

oai_token-act-pair · gemini-2.0-flash

v

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

 AssemblyProduct

-0.65

LEncoder

-0.63

 незавершена

-0.62

SharedDtor

-0.61

 propOrder

-0.60

 AssemblyVersion

-0.60

 noDo

-0.59

IUrlHelper

-0.59

Sucesor

-0.58

StructEnd

-0.58

POSITIVE LOGITS

ICTS

0.54

ilding

0.52

ftest

0.52

 getM

0.52

abases

0.52

seasonal

0.52

Seg

0.51

ViewFeatures

0.50

nthesis

0.49

ungsbedingungen

0.49

Activations Density 14.952%

the abbreviation "V" followed by zero to two more letters

v

No Comments

No Known Activations